{ "object_id": "https://biocomputeobject.org/GLY_000631/v-2.3.1", "spec_version": "1.3.0", "etag": "01733f9d76f70e618d6af97dc9189384", "provenance_domain": { "name": "Mouse O-GlcNAc Glycosylation Sites (MCW)", "version": "v-2.3.1", "created": "2022-08-16T20:48:29.540934", "modified": "2023-03-14T17:06:01.680Z", "embargo": { "start_time": "", "end_time": "" }, "contributors": [ { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "", "email": "jeetvora@gwu.edu" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Robel Kahsay", "email": "rykahsay@gwu.edu" }, { "affiliation": "Medical College of Wisconsin", "contribution": [ "contributedBy" ], "name": "Stephanie Olivier-Van Stichelen", "email": "solivier@mcw.edu" }, { "affiliation": "Medical College of Wisconsin", "contribution": [ "contributedBy" ], "name": "Eugenia Wulff-Fuentes", "email": "ewulff@mcw.edu" }, { "affiliation": "Medical College of Wisconsin", "contribution": [ "contributedBy" ], "name": " Rex R. Berendt", "email": "rberendt@mcw.edu" }, { "affiliation": "Medical College of Wisconsin", "contribution": [ "contributedBy" ], "name": " Logan Massman", "email": "lmassman@mcw.edu" }, { "affiliation": "Medical College of Wisconsin", "contribution": [ "contributedBy" ], "name": "Laura Danner", "email": "ldanner@mcw.edu" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Karina Martinez", "email": "karinamartinez@gwu.edu" }, { "name": "Jingyue Wu", "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "email": "jingyue.wu@email.gwu.edu" } ], "license": "https://creativecommons.org/licenses/by/4.0/" }, "usability_domain": [ "The Mouse O-GlcNAc Glycosylation Sites (MCW) contains mouse (taxid:10090) O-GlcNAc modifications on Serine and Threonine extracted from the publication and mapped to the UniProtKB canonical accession and fasta sequence. The GlyTouCan ID for the O-GlcNAc is G49108TO. The dataset also contains other information such as O-GlcNAc score, the count and the techniques used to determine the O-GlcNAc modification and the peptide sequence from the -5 to +5 postion of the modified residue. The dataset also containes disclaimer and notes where the position of sites in publication and in the fasta sequence varies.", "The dataset is contributed from The O-GlcNAc Database maintained by Stephanie Olivier's lab ", "Wulff-Fuentes E, Berendt RR, Massman L, Danner L, Malard F, Vora J, Kahsay R, and Olivier-Van Stichelen S, The Mouse O-GlcNAcome Database and Meta-Analysis. Scientific Data 8, 25 (2021) ", "QC check - The python script is used to process each protein entry of the database table and perform quality control (QC). In the QC checks, the reported UniProtKB accessions in the database are matched with the GlyGen\u2019s mouse protein master list of UniProtKB canonical accessions to ensure all of the proteins belong to mouse species. Next, the O-GlcNAc site data that contained the amino acid residue and its position are mapped to the GlyGen\u2019s fasta sequence for the corresponding mouse UniProtKB canonical proteins. The amino acid residues and positions that don't match with the fasta sequence of the canonical protein were flagged and excluded from the table. Similarly, the protein entries that don't have any site information are also excluded. The entries that passed all the quality control steps are exported as a final csv dataset file whereas the excluded entries are exported in a log file with the reasons for exclusion for further manual verification.", "DISCLAIMER - For each entry, an O-GlcNAc score was attributed to each O-GlcNAcylated protein, reflecting the confidence in the protein\u2019s O-GlcNAcylation identification. The score combined the number of articles and techniques used and the availability of some O-GlcNAcylation sites. Interestingly, a O-GlcNAc score of 3 or under, means that (1) no sites were identified, (2) only one technique was used, and (3) 1-2 articles were associated with the entry. Often identified from large-scale proteomics studies, at least an extra-validation step would be highly recommended to confirm their O-GlcNAcylation." ], "description_domain": { "keywords": [ "O-GlcNAc" ], "platform": [], "pipeline_steps": [ { "step_number": 1, "name": "make-proteoform-dataset.py", "description": "The script maps the UniProtKB accesions to the UniProtKB Canonical accessions and also checks the position and amino acid of O-GlcNAc modified residue against UniProtKB Canonical sequences. The script that processes this dataset matches the amino acid and position with the latest release fasta file as a QC check to eliminate the incorrect entries. The script also adds the -5 and +5 amino acids from the modified residue in the peptide field.", "version": "", "prerequisite": [], "input_list": [], "output_list": [] } ] }, "execution_domain": { "script": [ { "uri": { "uri": "https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py", "filename": "make-proteoform-dataset.py" } } ], "script_driver": "manual", "software_prerequisites": [ { "version": "2.7.5", "name": "Python", "uri": { "uri": "https://www.python.org/download/releases/2.7.5/" } } ], "external_data_endpoints": [], "environment_variables": {} }, "io_domain": { "input_subdomain": [ { "uri": { "filename": "mouse_protein_info_uniprotkb.csv", "uri": "https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/mouse_protein_info_uniprotkb.csv" } }, { "uri": { "filename": "mouse_protein_masterlist.csv", "uri": "https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/mouse_protein_masterlist.csv" } }, { "uri": { "filename": "mouse_protein_recnames.csv", "uri": "https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/mouse_protein_recnames.csv" } }, { "uri": { "filename": "sample_mapping.csv", "uri": "https:/data.glygen.org/ln2releases/data/v-2.3.1/misc/sample_mapping.csv" } }, { "uri": { "filename": "cellosaurus.txt", "uri": "https:/data.glygen.org/ln2downloads/cellosaurus/2023_10_11/cellosaurus.txt" } }, { "uri": { "filename": "mouse_o_glcnacome_mcw.csv", "uri": "https:/data.glygen.org/ln2downloads/mcw_oglcnac/2023_10_12/mouse_o_glcnacome_mcw.csv" } } ], "output_subdomain": [ { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/mouse_proteoform_glycosylation_sites_oglcnac_mcw.csv", "filename": "mouse_proteoform_glycosylation_sites_oglcnac_mcw.csv" } }, { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/mouse_proteoform_glycosylation_sites_oglcnac_mcw.stat.csv", "filename": "mouse_proteoform_glycosylation_sites_oglcnac_mcw.stat.csv" } } ] }, "error_domain": { "empirical_error": {}, "algorithmic_error": {} }, "extension_domain": [ { "extension_schema": "https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json", "dataset_extension": { "additional_license": { "data_license": "https://creativecommons.org/licenses/by/4.0/", "script_license": "https://www.gnu.org/licenses/gpl-3.0.en.html" }, "dataset_categories": [ { "category_value": "Mus musculus", "category_name": "species" }, { "category_value": "Proteoform", "category_name": "molecule" }, { "category_value": "O-GlcNAc Glycosylation Sites (MCW)", "category_name": "tag" }, { "category_value": "csv", "category_name": "file_type" }, { "category_value": "Reviewed", "category_name": "status" }, { "category_value": "internal", "category_name": "scope" } ] } } ] }